Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2456 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.8163. Min Act: -0.1700
Data Index: 7183775 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.5663. Min Act: -0.1700
Data Index: 2127756 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.3788. Min Act: -0.1700
Data Index: 965 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.3163. Min Act: -0.1700
Data Index: 4585395 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.3163. Min Act: -0.1700
Data Index: 5954617 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.3163. Min Act: -0.1700
Data Index: 8683627 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.1913. Min Act: -0.1700
Data Index: 6971615 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.2538. Min Act: -0.1700
Data Index: 5885490 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.1913. Min Act: -0.1700
Data Index: 7845179 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.1288. Min Act: -0.1700
Data Index: 2025058 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.1288. Min Act: -0.1700
Data Index: 6472704 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.0663. Min Act: -0.1700
Data Index: 23613 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.0663. Min Act: -0.1700
Data Index: 7849710 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.0663. Min Act: -0.1700
Data Index: 643216 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.0663. Min Act: -0.1700
Data Index: 587153 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.0038. Min Act: -0.1700
Data Index: 23612 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8163. Min Range: -9.8163
Max Act: 9.0038. Min Act: -0.1700
Data Index: 4410313 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8163. Min Range: -9.8163
Max Act: 8.9413. Min Act: -0.1700
Data Index: 7522738 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8163. Min Range: -9.8163
Max Act: 8.9413. Min Act: -0.1700
Data Index: 4787328 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8163. Min Range: -9.8163
Max Act: 8.9413. Min Act: -0.1700
Data Index: 333091 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19